pyspark 4.1.0.dev1__tar.gz → 4.1.0.dev3__tar.gz

pyspark-4.1.0.dev3/PKG-INFO

@@ -0,0 +1,92 @@
+Metadata-Version: 2.4
+Name: pyspark
+Version: 4.1.0.dev3
+Summary: Apache Spark Python API
+Home-page: https://github.com/apache/spark/tree/master/python
+Author: Spark Developers
+Author-email: dev@spark.apache.org
+License: Apache-2.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: py4j<0.10.9.10,>=0.10.9.7
+Provides-Extra: ml
+Requires-Dist: numpy>=1.21; extra == "ml"
+Provides-Extra: mllib
+Requires-Dist: numpy>=1.21; extra == "mllib"
+Provides-Extra: sql
+Requires-Dist: pandas>=2.2.0; extra == "sql"
+Requires-Dist: pyarrow>=15.0.0; extra == "sql"
+Requires-Dist: numpy>=1.21; extra == "sql"
+Provides-Extra: pandas-on-spark
+Requires-Dist: pandas>=2.2.0; extra == "pandas-on-spark"
+Requires-Dist: pyarrow>=15.0.0; extra == "pandas-on-spark"
+Requires-Dist: numpy>=1.21; extra == "pandas-on-spark"
+Provides-Extra: connect
+Requires-Dist: pandas>=2.2.0; extra == "connect"
+Requires-Dist: pyarrow>=15.0.0; extra == "connect"
+Requires-Dist: grpcio>=1.67.0; extra == "connect"
+Requires-Dist: grpcio-status>=1.67.0; extra == "connect"
+Requires-Dist: googleapis-common-protos>=1.65.0; extra == "connect"
+Requires-Dist: numpy>=1.21; extra == "connect"
+Provides-Extra: pipelines
+Requires-Dist: pandas>=2.2.0; extra == "pipelines"
+Requires-Dist: pyarrow>=15.0.0; extra == "pipelines"
+Requires-Dist: numpy>=1.21; extra == "pipelines"
+Requires-Dist: grpcio>=1.67.0; extra == "pipelines"
+Requires-Dist: grpcio-status>=1.67.0; extra == "pipelines"
+Requires-Dist: googleapis-common-protos>=1.65.0; extra == "pipelines"
+Requires-Dist: pyyaml>=3.11; extra == "pipelines"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Apache Spark
+
+Spark is a unified analytics engine for large-scale data processing. It provides
+high-level APIs in Scala, Java, Python, and R, and an optimized engine that
+supports general computation graphs for data analysis. It also supports a
+rich set of higher-level tools including Spark SQL for SQL and DataFrames,
+pandas API on Spark for pandas workloads, MLlib for machine learning, GraphX for graph processing,
+and Structured Streaming for stream processing.
+
+<https://spark.apache.org/>
+
+## Online Documentation
+
+You can find the latest Spark documentation, including a programming
+guide, on the [project web page](https://spark.apache.org/documentation.html)
+
+
+## Python Packaging
+
+This README file only contains basic information related to pip installed PySpark.
+This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility).
+Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at
+["Building Spark"](https://spark.apache.org/docs/latest/building-spark.html).
+
+The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN) - but does not contain the tools required to set up your own standalone Spark cluster. You can download the full version of Spark from the [Apache Spark downloads page](https://spark.apache.org/downloads.html).
+
+
+**NOTE:** If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.
+
+## Python Requirements
+
+At its core PySpark depends on Py4J, but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).
+See also [Dependencies](https://spark.apache.org/docs/latest/api/python/getting_started/install.html#dependencies) for production, and [dev/requirements.txt](https://github.com/apache/spark/blob/master/dev/requirements.txt) for development.

pyspark-4.1.0.dev3/deps/bin/load-spark-env.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# This script loads spark-env.sh if it exists, and ensures it is only loaded once.
+# spark-env.sh is loaded from SPARK_CONF_DIR if set, or within the current directory's
+# conf/ subdirectory.
+
+# Figure out where Spark is installed
+if [ -z "${SPARK_HOME}" ]; then
+  source "$(dirname "$0")"/find-spark-home
+fi
+
+SPARK_ENV_SH="spark-env.sh"
+if [ -z "$SPARK_ENV_LOADED" ]; then
+  export SPARK_ENV_LOADED=1
+
+  export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"${SPARK_HOME}"/conf}"
+
+  SPARK_ENV_SH="${SPARK_CONF_DIR}/${SPARK_ENV_SH}"
+  if [[ -f "${SPARK_ENV_SH}" ]]; then
+    # Promote all variable declarations to environment (exported) variables
+    set -a
+    . ${SPARK_ENV_SH}
+    set +a
+  fi
+fi
+
+# Setting SPARK_SCALA_VERSION if not already set.
+export SPARK_SCALA_VERSION=2.13
+#if [ -z "$SPARK_SCALA_VERSION" ]; then
+#  SCALA_VERSION_1=2.13
+#  SCALA_VERSION_2=2.12
+#
+#  ASSEMBLY_DIR_1="${SPARK_HOME}/assembly/target/scala-${SCALA_VERSION_1}"
+#  ASSEMBLY_DIR_2="${SPARK_HOME}/assembly/target/scala-${SCALA_VERSION_2}"
+#  ENV_VARIABLE_DOC="https://spark.apache.org/docs/latest/configuration.html#environment-variables"
+#  if [[ -d "$ASSEMBLY_DIR_1" && -d "$ASSEMBLY_DIR_2" ]]; then
+#    echo "Presence of build for multiple Scala versions detected ($ASSEMBLY_DIR_1 and $ASSEMBLY_DIR_2)." 1>&2
+#    echo "Remove one of them or, export SPARK_SCALA_VERSION=$SCALA_VERSION_1 in ${SPARK_ENV_SH}." 1>&2
+#    echo "Visit ${ENV_VARIABLE_DOC} for more details about setting environment variables in spark-env.sh." 1>&2
+#    exit 1
+#  fi
+#
+#  if [[ -d "$ASSEMBLY_DIR_1" ]]; then
+#    export SPARK_SCALA_VERSION=${SCALA_VERSION_1}
+#  else
+#    export SPARK_SCALA_VERSION=${SCALA_VERSION_2}
+#  fi
+#fi
+
+# Append jline option to enable the Beeline process to run in background.
+if [[ ( ! $(ps -o stat= -p $$ 2>/dev/null) =~ "+" ) && ! ( -p /dev/stdin ) ]]; then
+  export SPARK_BEELINE_OPTS="$SPARK_BEELINE_OPTS -Djline.terminal=jline.UnsupportedTerminal"
+fi

pyspark-4.1.0.dev3/deps/bin/spark-pipelines

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Default to standard python3 interpreter unless told otherwise
+if [[ -z "$PYSPARK_PYTHON" ]]; then
+  PYSPARK_PYTHON=python3
+fi
+
+if [ -z "${SPARK_HOME}" ]; then
+  source "$(dirname "$0")"/find-spark-home
+fi
+
+# Add the PySpark classes to the Python path:
+export PYTHONPATH="${SPARK_HOME}/python/:$PYTHONPATH"
+export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.9.9-src.zip:$PYTHONPATH"
+
+SDP_CLI_PY_FILE_PATH=$("${PYSPARK_PYTHON}" - <<'EOF'
+import pyspark, os
+from pathlib import Path
+print(Path(os.path.dirname(pyspark.__file__)) / "pipelines" / "cli.py")
+EOF
+)
+
+exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkPipelines "$SDP_CLI_PY_FILE_PATH" "$@"